paper-with-me

Papers

AdaSwarm: Augmenting Gradient-Based optimizers in Deep Learning with Swarm Intelligence

2020-05-19 · Rohan Mohapatra, Snehanshu Saha, Carlos A. Coello Coello, Anwesh Bhattacharya, Soma S. Dhavala, Sriparna Saha

This paper introduces AdaSwarm, a novel gradient-free optimizer which has similar or even better performance than the Adam optimizer adopted in neural networks. In order to support our proposed AdaSwarm, a novel Exponentially weighted Momentum Particle Swarm Optimizer (EMPSO), is proposed. The ability of AdaSwarm to tackle optimization problems is attributed to its capability to perform good gradient approximations. We show that, the gradient of any function, differentiable or not, can be approximated by using the parameters of EMPSO. This is a novel technique to simulate GD which lies at the boundary between numerical methods and swarm intelligence. Mathematical proofs of the gradient approximation produced are also provided. AdaSwarm competes closely with several state-of-the-art (SOTA) optimizers. We also show that AdaSwarm is able to handle a variety of loss functions during backpropagation, including the maximum absolute error (MAE).

📄 PDF Abstract BibTeX arXiv:2006.09875

Code (2)

anuwu/PSO-Grad 공식 구현
AdaSwarm/AdaSwarm pytorch

Tasks

Mathematical Proofs

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Modified swarm-based metaheuristics enhance Gradient Descent initialization performance: Application for EEG spatial filtering

2019-06-13 · Mojtaba Moattari, Mohammad Hassan Moradi, Reza Boostani

Gradient Descent (GD) approximators often fail in the solution space with multiple scales of convexities, i.e., in subspace learning and neural network scenarios. To handle that, one solution is to run GD multiple times …

EEGElectroencephalogram (EEG)

Color Image Segmentation Using Multi-Objective Swarm Optimizer and Multi-level Histogram Thresholding

2021-10-18 · Mohammadreza Naderi Boldaji, Samaneh Hosseini Semnani

Rapid developments in swarm intelligence optimizers and computer processing abilities make opportunities to design more accurate, stable, and comprehensive methods for color image segmentation. This paper presents a new …

Image SegmentationSegmentationSemantic SegmentationUnsupervised Image Segmentation

A Swarm Variant for the Schrödinger Solver

2021-04-10 · Urvil Nileshbhai Jivani, Omatharv Bharat Vaidya, Anwesh Bhattacharya, Snehanshu Saha

This paper introduces application of the Exponentially Averaged Momentum Particle Swarm Optimization (EM-PSO) as a derivative-free optimizer for Neural Networks. It adopts PSO's major advantages such as search space expl…

Mathematical Proofs

Large Language Models as Particle Swarm Optimizers

2025-04-12 · Yamato Shinohara, Jinglue Xu, Tianshui Li, Hitoshi Iba

Optimization problems often require domain-specific expertise to design problem-dependent methodologies. Recently, several approaches have gained attention by integrating large language models (LLMs) into genetic algorit…

Symbolic RegressionTraveling Salesman Problem

Hamiltonian Monte Carlo Particle Swarm Optimizer

2022-05-08 · Omatharv Bharat Vaidya, Rithvik Terence DSouza, Snehanshu Saha, Soma Dhavala 외

We introduce the Hamiltonian Monte Carlo Particle Swarm Optimizer (HMC-PSO), an optimization algorithm that reaps the benefits of both Exponentially Averaged Momentum PSO and HMC sampling. The coupling of the position an…

Position